OV - exec - Function qmcplusplus::BsplineFunctor<double>::evaluateVGL(int, int, int, double const*, double*, double*, double*, double*, int*) const

	Function: qmcplusplus::BsplineFunctor<double>::evaluateVGL(int, int, int, double const, double, do ...	Module: exec	Source: BsplineFunctor.h:291-339 [...]	Coverage (incl. loops): 0.36% \| (excl. loops): 0.01%

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h: 291 - 339

--------------------------------------------------------------------------------

291:   for (int jat = 0; jat < iLimit; jat++)

292:   {

293:     real_type r = distArray[jat];

294:     if (r < cutoff_radius && iStart + jat != iat)

295:     {

296:       distIndices[iCount]         = jat;

297:       distArrayCompressed[iCount] = r;

298:       iCount++;

299:     }

300:   }

301:

302:   #pragma omp simd

303:   for (int j = 0; j < iCount; j++)

304:   {

305:     real_type r    = distArrayCompressed[j];

306:     int iScatter   = distIndices[j];

307:     real_type rinv = cOne / r;

308:     r *= DeltaRInv;

309:     int iGather   = (int)r;

310:     real_type t   = r - real_type(iGather);

311:     real_type tp0 = t * t * t;

312:     real_type tp1 = t * t;

313:     real_type tp2 = t;

314:

315:     real_type sCoef0 = SplineCoefs[iGather + 0];

316:     real_type sCoef1 = SplineCoefs[iGather + 1];

317:     real_type sCoef2 = SplineCoefs[iGather + 2];

318:     real_type sCoef3 = SplineCoefs[iGather + 3];

319:

320:     // clang-format off

321:     laplArray[iScatter] = dSquareDeltaRinv *

322:       (sCoef0*( d2A[ 2]*tp2 + d2A[ 3])+

323:        sCoef1*( d2A[ 6]*tp2 + d2A[ 7])+

324:        sCoef2*( d2A[10]*tp2 + d2A[11])+

325:        sCoef3*( d2A[14]*tp2 + d2A[15]));

326:

327:     gradArray[iScatter] = DeltaRInv * rinv *

328:       (sCoef0*( dA[ 1]*tp1 + dA[ 2]*tp2 + dA[ 3])+

329:        sCoef1*( dA[ 5]*tp1 + dA[ 6]*tp2 + dA[ 7])+

330:        sCoef2*( dA[ 9]*tp1 + dA[10]*tp2 + dA[11])+

331:        sCoef3*( dA[13]*tp1 + dA[14]*tp2 + dA[15]));

332:

333:     valArray[iScatter] = (sCoef0*(A[ 0]*tp0 + A[ 1]*tp1 + A[ 2]*tp2 + A[ 3])+

334:         sCoef1*(A[ 4]*tp0 + A[ 5]*tp1 + A[ 6]*tp2 + A[ 7])+

335:         sCoef2*(A[ 8]*tp0 + A[ 9]*tp1 + A[10]*tp2 + A[11])+

336:         sCoef3*(A[12]*tp0 + A[13]*tp1 + A[14]*tp2 + A[15]));

337:     // clang-format on

338:   }

339: }

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h: 1064 - 1064

--------------------------------------------------------------------------------

1064: 	return *(this->_M_impl._M_start + __n);

0x236260 SUB	%EDX,%ECX

0x236262 JLE	236dd1

0x236268 PUSH	%RBP

0x236269 MOV	%RSP,%RBP

0x23626c PUSH	%R15

0x23626e PUSH	%R14

0x236270 PUSH	%R12

0x236272 PUSH	%RBX

0x236273 SUB	$0x370,%RSP

0x23627a VMOVSD	0x8(%RDI),%XMM0

0x23627f MOV	0x28(%RBP),%RAX

0x236283 MOV	0x20(%RBP),%R10

0x236287 MOVSXD	%EDX,%RBX

0x23628a MOVSXD	%ESI,%RSI

0x23628d LEA	(%R8,%RBX,8),%RDX

0x236291 MOV	%ECX,%R8D

0x236294 CMP	$0x1,%ECX

0x236297 JNE	2362a3

0x236299 XOR	%ECX,%ECX

0x23629b XOR	%R11D,%R11D

0x23629e JMP	236518

0x2362a3 VPBROADCASTQ	-0x320b4(%RIP),%XMM4

0x2362ac VMOVDQA	-0x31dd4(%RIP),%XMM5

0x2362b4 VPBROADCASTQ	-0x320dd(%RIP),%XMM6

0x2362bd VPBROADCASTD	-0x3221a(%RIP),%XMM7

0x2362c6 VMOVDDUP	%XMM0,%XMM1

0x2362ca MOV	%R8D,%ECX

0x2362cd AND	$-0x2,%ECX

0x2362d0 VPBROADCASTQ	%RBX,%XMM2

0x2362d6 VPBROADCASTQ	%RSI,%XMM3

0x2362dc XOR	%R14D,%R14D

0x2362df XOR	%R15D,%R15D

0x2362e2 XOR	%R11D,%R11D

0x2362e5 NOPW	%CS:(%RAX,%RAX,1)

(228) 0x2362f0 VMOVUPD	(%RDX,%R15,8),%XMM8

(228) 0x2362f6 VPADDQ	%XMM2,%XMM5,%XMM9

(228) 0x2362fa MOVSXD	%R11D,%R11

(228) 0x2362fd VPADDQ	%XMM6,%XMM5,%XMM5

(228) 0x236301 VPCMPNEQQ	%XMM3,%XMM9,%K1

(228) 0x236308 VCMPPD	$0x1,%XMM1,%XMM8,%K1{%K1}

(228) 0x23630f KMOVB	%K1,%R12D

(228) 0x236313 VPCOMPRESSD	%XMM4,(%RAX,%R11,4){%K1}

(228) 0x23631a VCOMPRESSPD	%XMM8,(%R10,%R11,8){%K1}

(228) 0x236321 VPADDD	%XMM7,%XMM4,%XMM4

(228) 0x236325 POPCNT	%R12D,%R12D

(228) 0x23632a KORTESTB	%K1,%K1

(228) 0x23632e CMOVE	%R14D,%R12D

(228) 0x236332 ADD	$0x2,%R15

(228) 0x236336 ADD	%R12D,%R11D

(228) 0x236339 CMP	%R15,%RCX

(228) 0x23633c JNE	2362f0

0x23633e CMP	%R8,%RCX

0x236341 JNE	236518

0x236347 TEST	%R11D,%R11D

0x23634a JLE	236dc2

0x236350 VMOVSD	0x68(%RDI),%XMM10

0x236355 VMOVSD	0x238(%RDI),%XMM0

0x23635d MOV	0x10(%RBP),%RDX

0x236361 VMOVSD	0x130(%RDI),%XMM5

0x236369 VMOVSD	0x148(%RDI),%XMM8

0x236371 VMOVSD	0x150(%RDI),%XMM11

0x236379 VMOVSD	0x168(%RDI),%XMM6

0x236381 VMOVSD	0x170(%RDI),%XMM7

0x236389 VMOVSD	0x188(%RDI),%XMM9

0x236391 VMOVSD	0x190(%RDI),%XMM16

0x236398 VMOVSD	0xa0(%RDI),%XMM13

0x2363a0 VMOVSD	0xa8(%RDI),%XMM14

0x2363a8 VMOVSD	0x128(%RDI),%XMM12

0x2363b0 VMOVSD	0xb0(%RDI),%XMM15

0x2363b8 VMOVSD	0xc0(%RDI),%XMM30

0x2363bf VMOVSD	0xc8(%RDI),%XMM17

0x2363c6 VMOVSD	0xd0(%RDI),%XMM18

0x2363cd VMOVSD	0xe0(%RDI),%XMM19

0x2363d4 VMOVSD	0xe8(%RDI),%XMM20

0x2363db VMOVSD	0xf0(%RDI),%XMM21

0x2363e2 VMOVSD	0x100(%RDI),%XMM22

0x2363e9 VMOVQ	0x108(%RDI),%XMM23

0x2363f0 VMOVSD	0x110(%RDI),%XMM24

0x2363f7 VMOVSD	0x18(%RDI),%XMM25

0x2363fe VMOVSD	0x20(%RDI),%XMM26

0x236405 VMOVSD	0x28(%RDI),%XMM27

0x23640c VMOVSD	0x30(%RDI),%XMM28

0x236413 VMOVSD	0x38(%RDI),%XMM29

0x23641a VMOVSD	0x40(%RDI),%XMM1

0x23641f VMOVSD	0x48(%RDI),%XMM2

0x236424 VMOVSD	0x50(%RDI),%XMM3

0x236429 VMOVSD	0x58(%RDI),%XMM31

0x236430 VMOVSD	0x60(%RDI),%XMM4

0x236435 LEA	(,%RBX,8),%RCX

0x23643d MOV	0x218(%RDI),%R8

0x236444 LEA	(%R9,%RBX,8),%RSI

0x236448 MOV	%R11D,%R9D

0x23644b ADD	%RCX,%RDX

0x23644e ADD	0x18(%RBP),%RCX

0x236452 VMOVAPS	%XMM10,-0x30(%RBP)

0x236457 VMOVSD	0x70(%RDI),%XMM10

0x23645c VMOVAPD	%XMM13,-0x410(%RBP)

0x236464 VMOVAPD	%XMM14,-0x400(%RBP)

0x23646c VMOVAPD	%XMM5,-0x2b0(%RBP)

0x236474 VMOVAPD	%XMM8,-0x2a0(%RBP)

0x23647c VMOVAPD	%XMM11,-0x290(%RBP)

0x236484 VMOVAPD	%XMM6,-0x280(%RBP)

0x23648c VMOVAPD	%XMM7,-0x270(%RBP)

0x236494 VMOVAPD	%XMM9,-0x260(%RBP)

0x23649c VMOVAPS	%XMM16,-0x250(%RBP)

0x2364a3 VMOVAPS	%XMM10,-0xc0(%RBP)

0x2364ab VMOVSD	0x78(%RDI),%XMM10

0x2364b0 VMOVAPS	%XMM10,-0xe0(%RBP)

0x2364b8 VMOVSD	0x80(%RDI),%XMM10

0x2364c0 VMOVAPS	%XMM10,-0xb0(%RBP)

0x2364c8 VMOVSD	0x88(%RDI),%XMM10

0x2364d0 VMOVAPS	%XMM10,-0xd0(%RBP)

0x2364d8 VMOVSD	0x90(%RDI),%XMM10

0x2364e0 VMOVAPS	%XMM10,-0xa0(%RBP)

0x2364e8 VMULSD	%XMM0,%XMM0,%XMM10

0x2364ec VMOVAPD	%XMM10,-0x3f0(%RBP)

0x2364f4 CMP	$0x1,%R11D

0x2364f8 JNE	23654e

0x2364fa VMOVAPD	-0x30(%RBP),%XMM16

0x236501 VMOVAPD	%XMM30,%XMM14

0x236507 XOR	%EDI,%EDI

0x236509 VMOVAPD	%XMM3,%XMM30

0x23650f VMOVAPD	%XMM4,%XMM13

0x236513 JMP	236af4

0x236518 SUB	%RBX,%RSI

0x23651b JMP	23652c

0x23651d NOPL	(%RAX)

(231) 0x236520 INC	%RCX

(231) 0x236523 CMP	%RCX,%R8

(231) 0x236526 JE	236347

(231) 0x23652c CMP	%RCX,%RSI

(231) 0x23652f JE	236520

(231) 0x236531 VMOVSD	(%RDX,%RCX,8),%XMM1

(231) 0x236536 VUCOMISD	%XMM0,%XMM1

(231) 0x23653a JAE	236520

(231) 0x23653c MOVSXD	%R11D,%R11

(231) 0x23653f MOV	%ECX,(%RAX,%R11,4)

(231) 0x236543 VMOVSD	%XMM1,(%R10,%R11,8)

(231) 0x236549 INC	%R11D

(231) 0x23654c JMP	236520

0x23654e VMOVAPD	%XMM1,-0x160(%RBP)

0x236556 VMOVDDUP	%XMM1,%XMM1

0x23655a VMOVAPD	%XMM17,-0x230(%RBP)

0x236561 VMOVDDUP	%XMM17,%XMM17

0x236567 VMOVDDUP	%XMM8,%XMM8

0x23656c VMOVDDUP	%XMM11,%XMM11

0x236571 VMOVDDUP	%XMM6,%XMM6

0x236575 VMOVAPD	%XMM18,-0x220(%RBP)

0x23657c VMOVAPD	%XMM19,-0x210(%RBP)

0x236583 VMOVDDUP	%XMM16,%XMM16

0x236589 VMOVDDUP	%XMM5,%XMM5

0x23658d VMOVDQA64	%XMM23,-0x1d0(%RBP)

0x236594 VMOVAPD	%XMM12,-0x120(%RBP)

0x23659c VMOVDDUP	%XMM12,%XMM12

0x2365a1 VMOVAPD	%XMM30,-0x90(%RBP)

0x2365a8 VMOVAPD	%XMM15,-0x240(%RBP)

0x2365b0 VMOVAPD	%XMM22,-0x1e0(%RBP)

0x2365b7 VMOVAPD	%XMM28,-0x180(%RBP)

0x2365be VMOVAPD	%XMM2,-0x150(%RBP)

0x2365c6 VMOVAPD	%XMM3,-0x140(%RBP)

0x2365ce VMOVDDUP	%XMM0,%XMM30

0x2365d4 VMOVDDUP	%XMM7,%XMM7

0x2365d8 VMOVDDUP	%XMM9,%XMM9

0x2365dd MOV	%R9D,%EDI

0x2365e0 AND	$-0x2,%EDI

0x2365e3 VMOVAPD	%XMM20,-0x200(%RBP)

0x2365ea VMOVAPD	%XMM21,-0x1f0(%RBP)

0x2365f1 VMOVAPD	%XMM24,-0x1c0(%RBP)

0x2365f8 VMOVAPD	%XMM25,-0x1b0(%RBP)

0x2365ff VMOVAPD	%XMM26,-0x1a0(%RBP)

0x236606 VMOVAPD	%XMM27,-0x190(%RBP)

0x23660d VMOVAPD	%XMM29,-0x170(%RBP)

0x236614 VMOVAPD	%XMM31,-0x130(%RBP)

0x23661b VMOVAPD	%XMM4,-0x110(%RBP)

0x236623 XOR	%R11D,%R11D

0x236626 VMOVAPD	%XMM1,-0x380(%RBP)

0x23662e VMOVDDUP	%XMM2,%XMM1

0x236632 VMOVAPD	%XMM17,-0xf0(%RBP)

0x236639 VMOVAPD	%XMM8,%XMM17

0x23663f VMOVDDUP	%XMM18,%XMM8

0x236645 VMOVAPD	%XMM11,%XMM18

0x23664b VMOVDDUP	%XMM19,%XMM11

0x236651 VMOVAPD	%XMM6,%XMM19

0x236657 VMOVDDUP	%XMM20,%XMM6

0x23665d VMOVAPS	%XMM16,-0x100(%RBP)

0x236664 VMOVAPD	%XMM5,%XMM16

0x23666a VMOVDDUP	%XMM10,%XMM5

0x23666f VMOVDDUP	%XMM13,%XMM10

0x236674 VMOVDDUP	%XMM14,%XMM13

0x236679 VMOVDDUP	%XMM15,%XMM14

0x23667e VMOVAPD	%XMM12,%XMM15

0x236683 VBROADCASTSS	-0x325dc(%RIP),%XMM2

0x23668c VMOVDDUP	-0x90(%RBP),%XMM12

0x236694 VMOVAPD	%XMM7,%XMM20

0x23669a VMOVAPD	%XMM1,-0x370(%RBP)

0x2366a2 VMOVDDUP	%XMM3,%XMM1

0x2366a6 VMOVAPD	%XMM6,-0x70(%RBP)

0x2366ab VMOVDDUP	%XMM21,%XMM6

0x2366b1 VBROADCASTSS	-0x3260e(%RIP),%XMM3

0x2366ba VMOVAPD	%XMM11,-0x80(%RBP)

0x2366bf VMOVAPD	%XMM9,%XMM21

0x2366c5 VMOVAPD	%XMM1,-0x360(%RBP)

0x2366cd VMOVDDUP	%XMM31,%XMM1

0x2366d3 VMOVAPD	%XMM6,-0x60(%RBP)

0x2366d8 VMOVDDUP	%XMM22,%XMM6

0x2366de VMOVAPD	-0x100(%RBP),%XMM22

0x2366e5 VMOVAPD	%XMM1,-0x350(%RBP)

0x2366ed VMOVDDUP	%XMM4,%XMM1

0x2366f1 VMOVAPD	%XMM6,-0x50(%RBP)

0x2366f6 VPBROADCASTQ	%XMM23,%XMM6

0x2366fc VMOVAPD	%XMM5,%XMM23

0x236702 VMOVDDUP	%XMM24,%XMM5

0x236708 VMOVAPD	%XMM10,%XMM24

0x23670e VMOVAPD	%XMM1,-0x340(%RBP)

0x236716 VMOVDDUP	-0x30(%RBP),%XMM1

0x23671b VMOVAPD	%XMM5,-0x3e0(%RBP)

0x236723 VMOVDDUP	%XMM25,%XMM5

0x236729 VMOVDQA	%XMM6,-0x40(%RBP)

0x23672e VMOVAPD	%XMM13,%XMM25

0x236734 VMOVAPD	%XMM2,-0x2c0(%RBP)

0x23673c VMOVAPD	%XMM5,-0x3d0(%RBP)

0x236744 VMOVDDUP	%XMM26,%XMM5

0x23674a VMOVAPD	%XMM14,%XMM26

0x236750 VMOVAPD	%XMM3,-0x2d0(%RBP)

0x236758 VMOVAPD	%XMM5,-0x3c0(%RBP)

0x236760 VMOVDDUP	%XMM27,%XMM5

0x236766 VMOVAPD	%XMM12,%XMM27

0x23676c VMOVAPD	%XMM5,-0x3b0(%RBP)

0x236774 VMOVDDUP	%XMM28,%XMM5

0x23677a VMOVAPD	-0xf0(%RBP),%XMM28

0x236781 VMOVAPS	%XMM1,-0x330(%RBP)

0x236789 VMOVAPS	-0xc0(%RBP),%XMM1

0x236791 VMOVAPD	%XMM5,-0x3a0(%RBP)

0x236799 VMOVDDUP	%XMM29,%XMM5

0x23679f VMOVAPD	%XMM8,%XMM29

0x2367a5 VMOVAPD	%XMM5,-0x390(%RBP)

0x2367ad VMOVDDUP	%XMM1,%XMM1

0x2367b1 VMOVAPS	%XMM1,-0x320(%RBP)

0x2367b9 VMOVDDUP	-0xe0(%RBP),%XMM1

0x2367c1 VMOVAPS	%XMM1,-0x310(%RBP)

0x2367c9 VMOVAPS	-0xb0(%RBP),%XMM1

0x2367d1 VMOVDDUP	%XMM1,%XMM1

0x2367d5 VMOVAPS	%XMM1,-0x300(%RBP)

0x2367dd VMOVDDUP	-0xd0(%RBP),%XMM1

0x2367e5 VMOVAPS	%XMM1,-0x2f0(%RBP)

0x2367ed VMOVAPD	-0xa0(%RBP),%XMM1

0x2367f5 VMOVDDUP	%XMM1,%XMM1

0x2367f9 VMOVAPD	%XMM1,-0x2e0(%RBP)

0x236801 NOPW	%CS:(%RAX,%RAX,1)

(229) 0x236810 VMOVAPD	(%R10,%R11,8),%XMM31

(229) 0x236817 VMOVAPD	-0x3a0(%RBP),%XMM13

(229) 0x23681f VMULPD	%XMM30,%XMM31,%XMM1

(229) 0x236825 VCVTTPD2DQ	%XMM1,%XMM3

(229) 0x236829 VROUNDPD	$0xb,%XMM1,%XMM2

(229) 0x23682f VPMOVSXDQ	%XMM3,%XMM5

(229) 0x236834 VSUBPD	%XMM2,%XMM1,%XMM7

(229) 0x236838 VPCMPEQD	%XMM2,%XMM2,%XMM2

(229) 0x23683c VPSUBD	%XMM2,%XMM3,%XMM6

(229) 0x236840 VMOVQ	%XMM5,%RBX

(229) 0x236845 VPEXTRQ	$0x1,%XMM5,%R14

(229) 0x23684b VPMOVSXDQ	%XMM6,%XMM6

(229) 0x236850 VMOVSD	(%R8,%RBX,8),%XMM5

(229) 0x236856 VMOVAPD	%XMM7,%XMM2

(229) 0x23685a VFMADD213PD	%XMM16,%XMM15,%XMM2

(229) 0x236860 VMULPD	%XMM7,%XMM7,%XMM9

(229) 0x236864 VMOVAPD	%XMM7,%XMM8

(229) 0x236868 VFMADD213PD	%XMM18,%XMM17,%XMM8

(229) 0x23686e VMOVHPD	(%R8,%R14,8),%XMM5,%XMM10

(229) 0x236874 VMOVQ	%XMM6,%RBX

(229) 0x236879 VPEXTRQ	$0x1,%XMM6,%R15

(229) 0x23687f VMOVSD	(%R8,%RBX,8),%XMM5

(229) 0x236885 VMOVHPD	(%R8,%R15,8),%XMM5,%XMM5

(229) 0x23688b VMOVAPD	%XMM9,%XMM4

(229) 0x23688f VFMADD213PD	%XMM26,%XMM24,%XMM4

(229) 0x236895 VMULPD	%XMM7,%XMM9,%XMM1

(229) 0x236899 VMOVAPD	%XMM1,%XMM11

(229) 0x23689d VFMADD231PD	%XMM7,%XMM25,%XMM4

(229) 0x2368a3 VMULPD	%XMM2,%XMM10,%XMM2

(229) 0x2368a7 VMULPD	%XMM4,%XMM10,%XMM4

(229) 0x2368ab VFMADD213PD	%XMM2,%XMM5,%XMM8

(229) 0x2368b0 VMOVAPD	%XMM9,%XMM2

(229) 0x2368b4 VFMADD213PD	%XMM29,%XMM27,%XMM2

(229) 0x2368ba VFMADD231PD	%XMM7,%XMM28,%XMM2

(229) 0x2368c0 VFMADD213PD	%XMM4,%XMM5,%XMM2

(229) 0x2368c5 VMOVAPD	%XMM1,%XMM4

(229) 0x2368c9 VFMADD132PD	-0x3d0(%RBP),%XMM13,%XMM4

(229) 0x2368d2 VMOVAPD	-0x360(%RBP),%XMM13

(229) 0x2368da VFMADD132PD	-0x390(%RBP),%XMM13,%XMM11

(229) 0x2368e3 VMOVAPD	-0x60(%RBP),%XMM13

(229) 0x2368e8 VFMADD231PD	-0x3c0(%RBP),%XMM9,%XMM4

(229) 0x2368f1 VFMADD231PD	-0x380(%RBP),%XMM9,%XMM11

(229) 0x2368fa VFMADD231PD	-0x3b0(%RBP),%XMM7,%XMM4

(229) 0x236903 VFMADD231PD	-0x370(%RBP),%XMM7,%XMM11

(229) 0x23690c VMULPD	%XMM4,%XMM10,%XMM4

(229) 0x236910 VMOVAPD	%XMM9,%XMM10

(229) 0x236915 VFMADD132PD	-0x80(%RBP),%XMM13,%XMM10

(229) 0x23691b VMOVAPD	-0x320(%RBP),%XMM13

(229) 0x236923 VFMADD213PD	%XMM4,%XMM5,%XMM11

(229) 0x236928 VPADDD	-0x2d0(%RBP),%XMM3,%XMM5

(229) 0x236930 VMOVAPD	%XMM7,%XMM4

(229) 0x236934 VFMADD213PD	%XMM20,%XMM19,%XMM4

(229) 0x23693a VPADDD	-0x2c0(%RBP),%XMM3,%XMM3

(229) 0x236942 VFMADD231PD	-0x70(%RBP),%XMM7,%XMM10

(229) 0x236948 VPMOVSXDQ	%XMM5,%XMM5

(229) 0x23694d VPMOVSXDQ	%XMM3,%XMM3

(229) 0x236952 VMOVQ	%XMM5,%RBX

(229) 0x236957 VPEXTRQ	$0x1,%XMM5,%R14

(229) 0x23695d VMOVSD	(%R8,%RBX,8),%XMM5

(229) 0x236963 VMOVQ	%XMM3,%RBX

(229) 0x236968 VMOVHPD	(%R8,%R14,8),%XMM5,%XMM5

(229) 0x23696e VPEXTRQ	$0x1,%XMM3,%R14

(229) 0x236974 VMOVSD	(%R8,%RBX,8),%XMM3

(229) 0x23697a VMOVHPD	(%R8,%R14,8),%XMM3,%XMM3

(229) 0x236980 VFMADD213PD	%XMM2,%XMM5,%XMM10

(229) 0x236985 VMOVAPD	%XMM1,%XMM2

(229) 0x236989 VFMADD132PD	-0x350(%RBP),%XMM13,%XMM2

(229) 0x236992 VFMADD213PD	%XMM8,%XMM5,%XMM4

(229) 0x236997 VFMADD231PD	-0x340(%RBP),%XMM9,%XMM2

(229) 0x2369a0 VFMADD231PD	-0x330(%RBP),%XMM7,%XMM2

(229) 0x2369a9 VFMADD213PD	%XMM11,%XMM5,%XMM2

(229) 0x2369ae VMOVAPD	-0x2e0(%RBP),%XMM5

(229) 0x2369b6 VFMADD132PD	-0x310(%RBP),%XMM5,%XMM1

(229) 0x2369bf VMOVAPD	-0x3e0(%RBP),%XMM5

(229) 0x2369c7 VFMADD231PD	-0x300(%RBP),%XMM9,%XMM1

(229) 0x2369d0 VFMADD132PD	-0x50(%RBP),%XMM5,%XMM9

(229) 0x2369d6 VFMADD231PD	-0x2f0(%RBP),%XMM7,%XMM1

(229) 0x2369df VFMADD231PD	-0x40(%RBP),%XMM7,%XMM9

(229) 0x2369e5 VFMADD213PD	%XMM22,%XMM21,%XMM7

(229) 0x2369eb VFMADD213PD	%XMM4,%XMM3,%XMM7

(229) 0x2369f0 VFMADD213PD	%XMM2,%XMM3,%XMM1

(229) 0x2369f5 VPMOVSXDQ	(%RAX,%R11,4),%XMM2

(229) 0x2369fb VFMADD213PD	%XMM10,%XMM3,%XMM9

(229) 0x236a00 VMULPD	%XMM7,%XMM23,%XMM3

(229) 0x236a06 ADD	$0x2,%R11

(229) 0x236a0a VMOVQ	%XMM2,%R14

(229) 0x236a0f VPEXTRQ	$0x1,%XMM2,%RBX

(229) 0x236a15 VMULPD	%XMM30,%XMM9,%XMM2

(229) 0x236a1b VMOVLPD	%XMM3,(%RCX,%R14,8)

(229) 0x236a21 VMOVLPD	%XMM1,(%RSI,%R14,8)

(229) 0x236a27 VMOVHPD	%XMM3,(%RCX,%RBX,8)

(229) 0x236a2c VMOVHPD	%XMM1,(%RSI,%RBX,8)

(229) 0x236a31 VDIVPD	%XMM31,%XMM2,%XMM2

(229) 0x236a37 VMOVLPD	%XMM2,(%RDX,%R14,8)

(229) 0x236a3d VMOVHPD	%XMM2,(%RDX,%RBX,8)

(229) 0x236a42 CMP	%R11,%RDI

(229) 0x236a45 JNE	236810

0x236a4b VMOVAPD	-0x240(%RBP),%XMM15

0x236a53 VMOVAPD	-0x90(%RBP),%XMM14

0x236a5b VMOVAPD	-0x230(%RBP),%XMM17

0x236a62 VMOVAPD	-0x220(%RBP),%XMM18

0x236a69 VMOVAPD	-0x210(%RBP),%XMM19

0x236a70 VMOVAPD	-0x200(%RBP),%XMM20

0x236a77 VMOVAPD	-0x1f0(%RBP),%XMM21

0x236a7e VMOVAPD	-0x1e0(%RBP),%XMM22

0x236a85 VMOVDQA64	-0x1d0(%RBP),%XMM23

0x236a8c VMOVAPD	-0x1c0(%RBP),%XMM24

0x236a93 VMOVAPD	-0x1b0(%RBP),%XMM25

0x236a9a VMOVAPD	-0x1a0(%RBP),%XMM26

0x236aa1 VMOVAPD	-0x190(%RBP),%XMM27

0x236aa8 VMOVAPD	-0x180(%RBP),%XMM28

0x236aaf VMOVAPD	-0x170(%RBP),%XMM29

0x236ab6 VMOVAPD	-0x160(%RBP),%XMM1

0x236abe VMOVAPD	-0x150(%RBP),%XMM2

0x236ac6 VMOVAPD	-0x140(%RBP),%XMM30

0x236acd VMOVAPD	-0x130(%RBP),%XMM31

0x236ad4 VMOVAPD	-0x110(%RBP),%XMM13

0x236adc VMOVAPD	-0x30(%RBP),%XMM16

0x236ae3 VMOVAPD	-0x120(%RBP),%XMM12

0x236aeb CMP	%R9,%RDI

0x236aee JE	236dc2

0x236af4 VMOVAPS	-0x280(%RBP),%XMM3

0x236afc VUNPCKLPD	-0x260(%RBP),%XMM3,%XMM3

0x236b04 VMOVAPS	%XMM3,-0x70(%RBP)

0x236b09 VMOVAPS	-0x270(%RBP),%XMM3

0x236b11 VUNPCKLPD	-0x250(%RBP),%XMM3,%XMM3

0x236b19 VMOVAPS	%XMM3,-0x60(%RBP)

0x236b1e VUNPCKLPD	-0x2a0(%RBP),%XMM12,%XMM3

0x236b26 VMOVAPD	%XMM3,-0x50(%RBP)

0x236b2b VMOVAPD	-0x2b0(%RBP),%XMM3

0x236b33 VUNPCKLPD	-0x290(%RBP),%XMM3,%XMM3

0x236b3b VMOVAPD	%XMM3,-0x40(%RBP)

(230) 0x236b40 VMOVSD	(%R10,%RDI,8),%XMM3

(230) 0x236b46 VMULSD	%XMM0,%XMM3,%XMM6

(230) 0x236b4a VMOVSD	%XMM3,-0x80(%RBP)

(230) 0x236b4f VMOVAPD	%XMM0,%XMM3

(230) 0x236b53 VROUNDSD	$0xb,%XMM6,%XMM6,%XMM4

(230) 0x236b59 VCVTTSD2SI	%XMM6,%R11D

(230) 0x236b5d VMOVAPD	%XMM14,%XMM0

(230) 0x236b61 MOVSXD	%R11D,%R11

(230) 0x236b64 VMOVSD	0x8(%R8,%R11,8),%XMM8

(230) 0x236b6b VSUBSD	%XMM4,%XMM6,%XMM5

(230) 0x236b6f VMOVUPD	(%R8,%R11,8),%XMM6

(230) 0x236b75 VMULSD	%XMM5,%XMM5,%XMM9

(230) 0x236b79 VMOVAPD	%XMM9,%XMM7

(230) 0x236b7d VFMADD132SD	-0x410(%RBP),%XMM15,%XMM7

(230) 0x236b86 VMOVAPD	%XMM9,%XMM12

(230) 0x236b8b VFMADD213SD	%XMM18,%XMM14,%XMM12

(230) 0x236b91 VMULSD	%XMM5,%XMM9,%XMM11

(230) 0x236b95 VMOVAPD	%XMM16,%XMM14

(230) 0x236b9b VMOVAPD	%XMM31,%XMM16

(230) 0x236ba1 VMOVAPD	%XMM9,%XMM10

(230) 0x236ba6 VMOVAPD	%XMM11,%XMM4

(230) 0x236baa VFMADD213SD	%XMM28,%XMM25,%XMM4

(230) 0x236bb0 VFMADD231SD	-0x400(%RBP),%XMM5,%XMM7

(230) 0x236bb9 VFMADD231SD	%XMM5,%XMM17,%XMM12

(230) 0x236bbf VFMADD231SD	%XMM9,%XMM26,%XMM4

(230) 0x236bc5 VFMADD231SD	%XMM5,%XMM27,%XMM4

(230) 0x236bcb VMULSD	%XMM6,%XMM7,%XMM7

(230) 0x236bcf VMULSD	%XMM6,%XMM4,%XMM4

(230) 0x236bd3 VFMADD213SD	%XMM7,%XMM8,%XMM12

(230) 0x236bd8 VMOVAPD	%XMM11,%XMM7

(230) 0x236bdc VFMADD213SD	%XMM30,%XMM29,%XMM7

(230) 0x236be2 VFMADD231SD	%XMM9,%XMM1,%XMM7

(230) 0x236be7 VFMADD231SD	%XMM5,%XMM2,%XMM7

(230) 0x236bec VFMADD213SD	%XMM4,%XMM8,%XMM7

(230) 0x236bf1 VMOVAPD	%XMM11,%XMM4

(230) 0x236bf5 VFMADD213SD	-0xc0(%RBP),%XMM31,%XMM4

(230) 0x236bfc VMOVAPD	%XMM30,%XMM31

(230) 0x236c02 VMOVAPD	%XMM29,%XMM30

(230) 0x236c08 VMOVAPD	%XMM28,%XMM29

(230) 0x236c0e VMOVAPD	%XMM27,%XMM28

(230) 0x236c14 VMOVAPD	%XMM26,%XMM27

(230) 0x236c1a VMOVAPD	%XMM25,%XMM26

(230) 0x236c20 VMOVAPD	%XMM24,%XMM25

(230) 0x236c26 VMOVDQA64	%XMM23,%XMM24

(230) 0x236c2c VMOVAPD	%XMM22,%XMM23

(230) 0x236c32 VMOVAPD	%XMM21,%XMM22

(230) 0x236c38 VMOVAPD	%XMM20,%XMM21

(230) 0x236c3e VMOVAPD	%XMM19,%XMM20

(230) 0x236c44 VMOVAPD	%XMM18,%XMM19

(230) 0x236c4a VMOVAPD	%XMM17,%XMM18

(230) 0x236c50 VMOVAPD	%XMM15,%XMM17

(230) 0x236c56 VMOVAPD	%XMM13,%XMM15

(230) 0x236c5b VMOVAPD	%XMM9,%XMM8

(230) 0x236c60 VFMADD231SD	%XMM9,%XMM13,%XMM4

(230) 0x236c65 VMOVAPD	%XMM2,%XMM13

(230) 0x236c69 VMOVAPD	%XMM1,%XMM2

(230) 0x236c6d VMOVAPD	-0xa0(%RBP),%XMM1

(230) 0x236c75 VFMADD132SD	-0xe0(%RBP),%XMM1,%XMM11

(230) 0x236c7e VMOVAPD	%XMM2,%XMM1

(230) 0x236c82 VMOVAPD	%XMM13,%XMM2

(230) 0x236c86 VMOVAPD	%XMM15,%XMM13

(230) 0x236c8b VMOVAPD	%XMM17,%XMM15

(230) 0x236c91 VMOVAPD	%XMM18,%XMM17

(230) 0x236c97 VMOVAPD	%XMM19,%XMM18

(230) 0x236c9d VMOVAPD	%XMM20,%XMM19

(230) 0x236ca3 VMOVAPD	%XMM21,%XMM20

(230) 0x236ca9 VMOVAPD	%XMM22,%XMM21

(230) 0x236caf VFMADD213SD	%XMM21,%XMM19,%XMM10

(230) 0x236cb5 VMOVAPD	%XMM23,%XMM22

(230) 0x236cbb VMOVDQA64	%XMM24,%XMM23

(230) 0x236cc1 VMOVAPD	%XMM25,%XMM24

(230) 0x236cc7 VMOVAPD	%XMM26,%XMM25

(230) 0x236ccd VMOVAPD	%XMM27,%XMM26

(230) 0x236cd3 VMOVAPD	%XMM28,%XMM27

(230) 0x236cd9 VMOVAPD	%XMM29,%XMM28

(230) 0x236cdf VMOVAPD	%XMM30,%XMM29

(230) 0x236ce5 VMOVAPD	%XMM31,%XMM30

(230) 0x236ceb VMOVAPD	%XMM16,%XMM31

(230) 0x236cf1 VMOVAPD	%XMM14,%XMM16

(230) 0x236cf7 VFMADD213SD	%XMM24,%XMM22,%XMM8

(230) 0x236cfd VMOVAPD	%XMM0,%XMM14

(230) 0x236d01 VMOVAPD	%XMM3,%XMM0

(230) 0x236d05 VMOVAPD	-0x40(%RBP),%XMM3

(230) 0x236d0a VFMADD231SD	%XMM5,%XMM16,%XMM4

(230) 0x236d10 VFMADD231SD	-0xb0(%RBP),%XMM9,%XMM11

(230) 0x236d19 VMOVUPD	0x10(%R8,%R11,8),%XMM9

(230) 0x236d20 VFMADD231SD	%XMM5,%XMM20,%XMM10

(230) 0x236d26 VFMADD231SD	%XMM5,%XMM23,%XMM8

(230) 0x236d2c VFMADD213SD	%XMM7,%XMM9,%XMM4

(230) 0x236d31 VMOVAPD	-0xd0(%RBP),%XMM7

(230) 0x236d39 VFMADD213SD	%XMM12,%XMM9,%XMM10

(230) 0x236d3e VMOVSD	0x18(%R8,%R11,8),%XMM12

(230) 0x236d45 MOVSXD	(%RAX,%RDI,4),%R11

(230) 0x236d49 INC	%RDI

(230) 0x236d4c VFMADD231SD	%XMM5,%XMM7,%XMM11

(230) 0x236d51 VFMADD213SD	%XMM10,%XMM12,%XMM8

(230) 0x236d56 VMOVAPD	-0x3f0(%RBP),%XMM10

(230) 0x236d5e VFMADD213SD	%XMM4,%XMM12,%XMM11

(230) 0x236d63 VMOVDDUP	%XMM5,%XMM4

(230) 0x236d67 VMOVAPD	%XMM4,%XMM5

(230) 0x236d6b VFMADD132PD	-0x50(%RBP),%XMM3,%XMM5

(230) 0x236d71 VMOVAPD	-0x60(%RBP),%XMM3

(230) 0x236d76 VFMADD132PD	-0x70(%RBP),%XMM3,%XMM4

(230) 0x236d7c VMULSD	%XMM0,%XMM8,%XMM3

(230) 0x236d80 VDIVSD	-0x80(%RBP),%XMM3,%XMM3

(230) 0x236d85 VMOVSD	%XMM11,(%RSI,%R11,8)

(230) 0x236d8b VMULPD	%XMM6,%XMM5,%XMM5

(230) 0x236d8f VMULPD	%XMM4,%XMM9,%XMM4

(230) 0x236d93 VSHUFPD	$0x1,%XMM5,%XMM5,%XMM6

(230) 0x236d98 VADDSD	%XMM5,%XMM6,%XMM5

(230) 0x236d9c VADDSD	%XMM4,%XMM5,%XMM5

(230) 0x236da0 VSHUFPD	$0x1,%XMM4,%XMM4,%XMM4

(230) 0x236da5 VADDSD	%XMM4,%XMM5,%XMM4

(230) 0x236da9 VMOVSD	%XMM3,(%RDX,%R11,8)

(230) 0x236daf VMULSD	%XMM4,%XMM10,%XMM4

(230) 0x236db3 VMOVSD	%XMM4,(%RCX,%R11,8)

(230) 0x236db9 CMP	%RDI,%R9

(230) 0x236dbc JNE	236b40

0x236dc2 ADD	$0x370,%RSP

0x236dc9 POP	%RBX

0x236dca POP	%R12

0x236dcc POP	%R14

0x236dce POP	%R15

0x236dd0 POP	%RBP

0x236dd1 RET

0x236dd2 INT	$0x3

0x236dd3 INT	$0x3

0x236dd4 INT	$0x3

0x236dd5 INT	$0x3

0x236dd6 INT	$0x3

0x236dd7 INT	$0x3

0x236dd8 INT	$0x3

0x236dd9 INT	$0x3

0x236dda INT	$0x3

0x236ddb INT	$0x3

0x236ddc INT	$0x3

0x236ddd INT	$0x3

0x236dde INT	$0x3

0x236ddf INT	$0x3

Coverage (%)	Name	Source Location	Module
►48.43+	miniqmcreference::TwoBodyJastr[...]	TwoBodyJastrowRef.h:274	exec
○	qmcplusplus::WaveFunction::acc[...]	NewTimer.h:249	exec
○	main.omp_outlined.64	stl_vector.h:1046	exec
○	__kmp_invoke_microtask		libomp.so
○	__kmp_invoke_task_func		libomp.so
○	__kmp_launch_thread		libomp.so
○	__kmp_launch_worker(void*)		libomp.so
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►40.53+	miniqmcreference::TwoBodyJastr[...]	TwoBodyJastrowRef.h:274	exec
○	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:201	exec
○	main.omp_outlined.64	stl_vector.h:1046	exec
○	__kmp_invoke_microtask		libomp.so
○	__kmp_invoke_task_func		libomp.so
○	__kmp_launch_thread		libomp.so
○	__kmp_launch_worker(void*)		libomp.so
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►5.02+	miniqmcreference::TwoBodyJastr[...]	TwoBodyJastrowRef.h:274	exec
○	miniqmcreference::TwoBodyJastr[...]	TwoBodyJastrowRef.h:422	exec
○	miniqmcreference::TwoBodyJastr[...]	TwoBodyJastrowRef.h:411	exec
○	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:175	exec
○	main.omp_outlined	miniqmc.cpp:379	exec
○	__kmp_invoke_microtask		libomp.so
○	__kmp_invoke_task_func		libomp.so
○	__kmp_launch_thread		libomp.so
○	__kmp_launch_worker(void*)		libomp.so
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►1.96+	miniqmcreference::OneBodyJastr[...]	OneBodyJastrowRef.h:218	exec
○	miniqmcreference::OneBodyJastr[...]	OneBodyJastrowRef.h:260	exec
○	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:201	exec
○	main.omp_outlined.64	stl_vector.h:1046	exec
○	__kmp_invoke_microtask		libomp.so
○	__kmp_invoke_task_func		libomp.so
○	__kmp_launch_thread		libomp.so
○	__kmp_launch_worker(void*)		libomp.so
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►1.52+	miniqmcreference::TwoBodyJastr[...]	TwoBodyJastrowRef.h:274	exec
○	qmcplusplus::WaveFunction::acc[...]	NewTimer.h:249	exec
○	main.omp_outlined.64	stl_vector.h:1046	exec
○	__kmp_invoke_microtask		libomp.so
○	__kmp_invoke_task_func		libomp.so
○	__kmp_fork_call		libomp.so
○	__kmpc_fork_call		libomp.so
○	main	miniqmc.cpp:411	exec
○	__libc_start_call_main		libc.so.6
►1.25+	miniqmcreference::TwoBodyJastr[...]	TwoBodyJastrowRef.h:274	exec
○	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:201	exec
○	main.omp_outlined.64	stl_vector.h:1046	exec
○	__kmp_invoke_microtask		libomp.so
○	__kmp_invoke_task_func		libomp.so
○	__kmp_fork_call		libomp.so
○	__kmpc_fork_call		libomp.so
○	main	miniqmc.cpp:411	exec
○	__libc_start_call_main		libc.so.6

min	med	avg	max

Percentile Index	10	20	30	40	50	60	70	80	90	100
Value

min	med	avg	max

Percentile Index	10	20	30	40	50	60	70	80	90	100
Value

Path /

Average path: Display a virtual path defined by average values of all real paths

The code analyzed by CQA in that panel excludes loops and represents 0.01% of application time for run aocc_4

Source file and lines	BsplineFunctor.h:291-339
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:291-339
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:1064

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Vectorization

Your function is partially vectorized. Only 18% of vector register length is used (average across all SSE/AVX instructions). By fully vectorizing your function, you can lower the cost of an iteration from 38.75 to 8.37 cycles (4.63x speedup).

Details

51% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

37% of SSE/AVX loads are used in vector version.
0% of SSE/AVX addition or subtraction instructions are used in vector version.
0% of SSE/AVX multiply instructions are used in vector version.
21% of SSE/AVX instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Since your execution units are vector units, only a fully vectorized function can use their full power.

Workaround

Try another compiler or update/tune your current one
Make array accesses unit-stride:
- If your function streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

Execution units bottlenecks

Performance is limited by:

reading data from caches/RAM (load units are a bottleneck)
writing data to caches/RAM (the store unit is a bottleneck)

By removing all these bottlenecks, you can lower the cost of an iteration from 38.75 to 33.50 cycles (1.16x speedup).

Workaround

Read less array elements
Write less array elements

No data for this section

Complex instructions

Detected COMPLEX INSTRUCTIONS.

Details

These instructions generate more than one micro-operation and only one of them can be decoded during a cycle and the extra micro-operations increase pressure on execution units.

VPBROADCASTQ: 2 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:291
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:291

Type of elements and instruction set

1 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in scalar mode (one at a time).

Matching between your function (in the source code) and the binary function

The binary function is composed of 1 FP arithmetical operations:

1: multiply

The binary function is loading 980 bytes (122 double precision FP elements). The binary function is storing 1072 bytes (134 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.00 FP operations per loaded or stored byte.

General properties

nb instructions	275
nb uops	260
loop length	1607
used x86 registers	15
used mmx registers	0
used xmm registers	32
used ymm registers	0
used zmm registers	0
nb stack references	67

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	32.50 cycles
front end	32.50 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	4.67	4.67	4.67	4.67	4.67	4.67	38.75	38.75	38.75	38.75	12.25	12.25	12.25	12.25	33.50	33.50
cycles	4.67	4.67	4.67	4.67	4.67	4.67	38.75	38.75	38.75	38.75	12.25	12.25	12.25	12.25	33.50	33.50

Execution ports to units layout:

P0: ALU
P1: ALU
P2: ALU
P3: ALU, BRU
P4: ALU, BRU
P5: ALU, BRU
P6 (512 bits): store address, load
P7 (512 bits): store address, load
P8 (512 bits): store address, load
P9 (512 bits): store address, load
P10 (512 bits): VPU, DIV/SQRT
P11 (512 bits): VPU, DIV/SQRT
P12 (512 bits): VPU
P13 (512 bits): VPU
P14 (512 bits): FP store data
P15 (512 bits): FP store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	32.50
Dispatch	38.75
Overall L1	38.75

Vectorization ratios

INT

all	12%
load	22%
store	100%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	0%

all	57%
load	38%
store	100%
mul	0%
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	28%

INT+FP

all	51%
load	37%
store	100%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	21%

Vector efficiency ratios

INT

all	11%
load	14%
store	25%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	10%
fma	NA (no fma vectorizable/vectorized instructions)
other	8%

all	19%
load	17%
store	25%
mul	12%
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	15%

INT+FP

all	18%
load	16%
store	25%
mul	12%
add-sub	10%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	13%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 38.75 cycles. At this rate:

9% of peak load performance is reached (25.29 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
21% of peak store performance is reached (27.66 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Found no such bottlenecks.

ASM code

In the binary file, the address of the function is: 236260

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	Latency	Recip. throughput	Vectorization
SUB %EDX,%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JLE 236dd1 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi+0xb71>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
PUSH %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB $0x370,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVSD 0x8(%RDI),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOV 0x28(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x20(%RBP),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
MOVSXD %EDX,%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOVSXD %ESI,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
LEA (%R8,%RBX,8),%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %ECX,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP $0x1,%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JNE 2362a3 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi+0x43>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
XOR %ECX,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
XOR %R11D,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
JMP 236518 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi+0x2b8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
VPBROADCASTQ -0x320b4(%RIP),%XMM4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
VMOVDQA -0x31dd4(%RIP),%XMM5	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VPBROADCASTQ -0x320dd(%RIP),%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
VPBROADCASTD -0x3221a(%RIP),%XMM7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (6.3%)
VMOVDDUP %XMM0,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOV %R8D,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
AND $-0x2,%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
VPBROADCASTQ %RBX,%XMM2	2	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	1	scal (12.5%)
VPBROADCASTQ %RSI,%XMM3	2	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	1	scal (12.5%)
XOR %R14D,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
XOR %R15D,%R15D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
XOR %R11D,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
CMP %R8,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JNE 236518 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi+0x2b8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
TEST %R11D,%R11D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JLE 236dc2 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi+0xb62>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
VMOVSD 0x68(%RDI),%XMM10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x238(%RDI),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOV 0x10(%RBP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
VMOVSD 0x130(%RDI),%XMM5	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x148(%RDI),%XMM8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x150(%RDI),%XMM11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x168(%RDI),%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x170(%RDI),%XMM7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x188(%RDI),%XMM9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x190(%RDI),%XMM16	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0xa0(%RDI),%XMM13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0xa8(%RDI),%XMM14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x128(%RDI),%XMM12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0xb0(%RDI),%XMM15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0xc0(%RDI),%XMM30	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0xc8(%RDI),%XMM17	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0xd0(%RDI),%XMM18	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0xe0(%RDI),%XMM19	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0xe8(%RDI),%XMM20	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0xf0(%RDI),%XMM21	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x100(%RDI),%XMM22	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVQ 0x108(%RDI),%XMM23	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x110(%RDI),%XMM24	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x18(%RDI),%XMM25	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x20(%RDI),%XMM26	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x28(%RDI),%XMM27	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x30(%RDI),%XMM28	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x38(%RDI),%XMM29	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x40(%RDI),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x48(%RDI),%XMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x50(%RDI),%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x58(%RDI),%XMM31	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x60(%RDI),%XMM4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
LEA (,%RBX,8),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV 0x218(%RDI),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
LEA (%R9,%RBX,8),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %R11D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
ADD %RCX,%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
ADD 0x18(%RBP),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
VMOVAPS %XMM10,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVSD 0x70(%RDI),%XMM10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVAPD %XMM13,-0x410(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM14,-0x400(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM5,-0x2b0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM8,-0x2a0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM11,-0x290(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM6,-0x280(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM7,-0x270(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM9,-0x260(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPS %XMM16,-0x250(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPS %XMM10,-0xc0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVSD 0x78(%RDI),%XMM10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVAPS %XMM10,-0xe0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVSD 0x80(%RDI),%XMM10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVAPS %XMM10,-0xb0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVSD 0x88(%RDI),%XMM10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVAPS %XMM10,-0xd0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVSD 0x90(%RDI),%XMM10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVAPS %XMM10,-0xa0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMULSD %XMM0,%XMM0,%XMM10	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VMOVAPD %XMM10,-0x3f0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
CMP $0x1,%R11D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JNE 23654e <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi+0x2ee>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
VMOVAPD -0x30(%RBP),%XMM16	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD %XMM30,%XMM14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
VMOVAPD %XMM3,%XMM30	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVAPD %XMM4,%XMM13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
JMP 236af4 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi+0x894>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
SUB %RBX,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JMP 23652c <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi+0x2cc>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
VMOVAPD %XMM1,-0x160(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM17,-0x230(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM17,%XMM17	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVDDUP %XMM8,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVDDUP %XMM11,%XMM11	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVDDUP %XMM6,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM18,-0x220(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM19,-0x210(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM16,%XMM16	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVDDUP %XMM5,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVDQA64 %XMM23,-0x1d0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM12,-0x120(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM12,%XMM12	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM30,-0x90(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM15,-0x240(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM22,-0x1e0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM28,-0x180(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM2,-0x150(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM3,-0x140(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM0,%XMM30	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVDDUP %XMM7,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVDDUP %XMM9,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOV %R9D,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x2,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVAPD %XMM20,-0x200(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM21,-0x1f0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM24,-0x1c0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM25,-0x1b0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM26,-0x1a0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM27,-0x190(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM29,-0x170(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM31,-0x130(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM4,-0x110(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
XOR %R11D,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
VMOVAPD %XMM1,-0x380(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM2,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM17,-0xf0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM8,%XMM17	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVDDUP %XMM18,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM11,%XMM18	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVDDUP %XMM19,%XMM11	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM6,%XMM19	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVDDUP %XMM20,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPS %XMM16,-0x100(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM5,%XMM16	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVDDUP %XMM10,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVDDUP %XMM13,%XMM10	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVDDUP %XMM14,%XMM13	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVDDUP %XMM15,%XMM14	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM12,%XMM15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VBROADCASTSS -0x325dc(%RIP),%XMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (6.3%)
VMOVDDUP -0x90(%RBP),%XMM12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
VMOVAPD %XMM7,%XMM20	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVAPD %XMM1,-0x370(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM3,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM6,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM21,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VBROADCASTSS -0x3260e(%RIP),%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (6.3%)
VMOVAPD %XMM11,-0x80(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM9,%XMM21	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVAPD %XMM1,-0x360(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM31,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM6,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM22,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD -0x100(%RBP),%XMM22	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD %XMM1,-0x350(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM4,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM6,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VPBROADCASTQ %XMM23,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM5,%XMM23	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVDDUP %XMM24,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM10,%XMM24	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVAPD %XMM1,-0x340(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP -0x30(%RBP),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
VMOVAPD %XMM5,-0x3e0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM25,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVDQA %XMM6,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM13,%XMM25	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVAPD %XMM2,-0x2c0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM5,-0x3d0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM26,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM14,%XMM26	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVAPD %XMM3,-0x2d0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM5,-0x3c0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM27,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM12,%XMM27	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVAPD %XMM5,-0x3b0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM28,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD -0xf0(%RBP),%XMM28	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPS %XMM1,-0x330(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPS -0xc0(%RBP),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD %XMM5,-0x3a0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM29,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM8,%XMM29	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVAPD %XMM5,-0x390(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPS %XMM1,-0x320(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP -0xe0(%RBP),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
VMOVAPS %XMM1,-0x310(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPS -0xb0(%RBP),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVDDUP %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPS %XMM1,-0x300(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP -0xd0(%RBP),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
VMOVAPS %XMM1,-0x2f0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD -0xa0(%RBP),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVDDUP %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM1,-0x2e0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
VMOVAPD -0x240(%RBP),%XMM15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x90(%RBP),%XMM14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x230(%RBP),%XMM17	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x220(%RBP),%XMM18	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x210(%RBP),%XMM19	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x200(%RBP),%XMM20	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x1f0(%RBP),%XMM21	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x1e0(%RBP),%XMM22	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVDQA64 -0x1d0(%RBP),%XMM23	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x1c0(%RBP),%XMM24	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x1b0(%RBP),%XMM25	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x1a0(%RBP),%XMM26	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x190(%RBP),%XMM27	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x180(%RBP),%XMM28	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x170(%RBP),%XMM29	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x160(%RBP),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x150(%RBP),%XMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x140(%RBP),%XMM30	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x130(%RBP),%XMM31	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x110(%RBP),%XMM13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x30(%RBP),%XMM16	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x120(%RBP),%XMM12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
CMP %R9,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JE 236dc2 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi+0xb62>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
VMOVAPS -0x280(%RBP),%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VUNPCKLPD -0x260(%RBP),%XMM3,%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
VMOVAPS %XMM3,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPS -0x270(%RBP),%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VUNPCKLPD -0x250(%RBP),%XMM3,%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
VMOVAPS %XMM3,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VUNPCKLPD -0x2a0(%RBP),%XMM12,%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
VMOVAPD %XMM3,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD -0x2b0(%RBP),%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VUNPCKLPD -0x290(%RBP),%XMM3,%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
VMOVAPD %XMM3,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
ADD $0x370,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A

The code analyzed by CQA in that panel excludes loops and represents 0.01% of application time for run aocc_4

Source file and lines	BsplineFunctor.h:291-339
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:291-339
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:1064

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Vectorization

Details

51% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

37% of SSE/AVX loads are used in vector version.
0% of SSE/AVX addition or subtraction instructions are used in vector version.
0% of SSE/AVX multiply instructions are used in vector version.
21% of SSE/AVX instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Since your execution units are vector units, only a fully vectorized function can use their full power.

Workaround

Try another compiler or update/tune your current one
Make array accesses unit-stride:
- If your function streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

Execution units bottlenecks

Performance is limited by:

reading data from caches/RAM (load units are a bottleneck)
writing data to caches/RAM (the store unit is a bottleneck)

By removing all these bottlenecks, you can lower the cost of an iteration from 38.75 to 33.50 cycles (1.16x speedup).

Workaround

Read less array elements
Write less array elements

No data for this section

Complex instructions

Detected COMPLEX INSTRUCTIONS.

Details

These instructions generate more than one micro-operation and only one of them can be decoded during a cycle and the extra micro-operations increase pressure on execution units.

VPBROADCASTQ: 2 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:291
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:291

Type of elements and instruction set

1 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in scalar mode (one at a time).

Matching between your function (in the source code) and the binary function

The binary function is composed of 1 FP arithmetical operations:

1: multiply

The binary function is loading 980 bytes (122 double precision FP elements). The binary function is storing 1072 bytes (134 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.00 FP operations per loaded or stored byte.

General properties

nb instructions	275
nb uops	260
loop length	1607
used x86 registers	15
used mmx registers	0
used xmm registers	32
used ymm registers	0
used zmm registers	0
nb stack references	67

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	32.50 cycles
front end	32.50 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	4.67	4.67	4.67	4.67	4.67	4.67	38.75	38.75	38.75	38.75	12.25	12.25	12.25	12.25	33.50	33.50
cycles	4.67	4.67	4.67	4.67	4.67	4.67	38.75	38.75	38.75	38.75	12.25	12.25	12.25	12.25	33.50	33.50

Execution ports to units layout:

P0: ALU
P1: ALU
P2: ALU
P3: ALU, BRU
P4: ALU, BRU
P5: ALU, BRU
P6 (512 bits): store address, load
P7 (512 bits): store address, load
P8 (512 bits): store address, load
P9 (512 bits): store address, load
P10 (512 bits): VPU, DIV/SQRT
P11 (512 bits): VPU, DIV/SQRT
P12 (512 bits): VPU
P13 (512 bits): VPU
P14 (512 bits): FP store data
P15 (512 bits): FP store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	32.50
Dispatch	38.75
Overall L1	38.75

Vectorization ratios

INT

all	12%
load	22%
store	100%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	0%

all	57%
load	38%
store	100%
mul	0%
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	28%

INT+FP

all	51%
load	37%
store	100%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	21%

Vector efficiency ratios

INT

all	11%
load	14%
store	25%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	10%
fma	NA (no fma vectorizable/vectorized instructions)
other	8%

all	19%
load	17%
store	25%
mul	12%
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	15%

INT+FP

all	18%
load	16%
store	25%
mul	12%
add-sub	10%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	13%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 38.75 cycles. At this rate:

9% of peak load performance is reached (25.29 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
21% of peak store performance is reached (27.66 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Found no such bottlenecks.

ASM code

In the binary file, the address of the function is: 236260

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	Latency	Recip. throughput	Vectorization
SUB %EDX,%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JLE 236dd1 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi+0xb71>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
PUSH %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB $0x370,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVSD 0x8(%RDI),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOV 0x28(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x20(%RBP),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
MOVSXD %EDX,%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOVSXD %ESI,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
LEA (%R8,%RBX,8),%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %ECX,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP $0x1,%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JNE 2362a3 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi+0x43>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
XOR %ECX,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
XOR %R11D,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
JMP 236518 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi+0x2b8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
VPBROADCASTQ -0x320b4(%RIP),%XMM4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
VMOVDQA -0x31dd4(%RIP),%XMM5	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VPBROADCASTQ -0x320dd(%RIP),%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
VPBROADCASTD -0x3221a(%RIP),%XMM7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (6.3%)
VMOVDDUP %XMM0,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOV %R8D,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
AND $-0x2,%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
VPBROADCASTQ %RBX,%XMM2	2	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	1	scal (12.5%)
VPBROADCASTQ %RSI,%XMM3	2	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	1	scal (12.5%)
XOR %R14D,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
XOR %R15D,%R15D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
XOR %R11D,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
CMP %R8,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JNE 236518 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi+0x2b8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
TEST %R11D,%R11D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JLE 236dc2 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi+0xb62>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
VMOVSD 0x68(%RDI),%XMM10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x238(%RDI),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOV 0x10(%RBP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
VMOVSD 0x130(%RDI),%XMM5	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x148(%RDI),%XMM8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x150(%RDI),%XMM11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x168(%RDI),%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x170(%RDI),%XMM7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x188(%RDI),%XMM9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x190(%RDI),%XMM16	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0xa0(%RDI),%XMM13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0xa8(%RDI),%XMM14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x128(%RDI),%XMM12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0xb0(%RDI),%XMM15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0xc0(%RDI),%XMM30	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0xc8(%RDI),%XMM17	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0xd0(%RDI),%XMM18	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0xe0(%RDI),%XMM19	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0xe8(%RDI),%XMM20	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0xf0(%RDI),%XMM21	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x100(%RDI),%XMM22	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVQ 0x108(%RDI),%XMM23	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x110(%RDI),%XMM24	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x18(%RDI),%XMM25	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x20(%RDI),%XMM26	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x28(%RDI),%XMM27	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x30(%RDI),%XMM28	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x38(%RDI),%XMM29	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x40(%RDI),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x48(%RDI),%XMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x50(%RDI),%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x58(%RDI),%XMM31	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVSD 0x60(%RDI),%XMM4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
LEA (,%RBX,8),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV 0x218(%RDI),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
LEA (%R9,%RBX,8),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %R11D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
ADD %RCX,%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
ADD 0x18(%RBP),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
VMOVAPS %XMM10,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVSD 0x70(%RDI),%XMM10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVAPD %XMM13,-0x410(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM14,-0x400(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM5,-0x2b0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM8,-0x2a0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM11,-0x290(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM6,-0x280(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM7,-0x270(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM9,-0x260(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPS %XMM16,-0x250(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPS %XMM10,-0xc0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVSD 0x78(%RDI),%XMM10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVAPS %XMM10,-0xe0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVSD 0x80(%RDI),%XMM10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVAPS %XMM10,-0xb0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVSD 0x88(%RDI),%XMM10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVAPS %XMM10,-0xd0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVSD 0x90(%RDI),%XMM10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVAPS %XMM10,-0xa0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMULSD %XMM0,%XMM0,%XMM10	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VMOVAPD %XMM10,-0x3f0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
CMP $0x1,%R11D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JNE 23654e <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi+0x2ee>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
VMOVAPD -0x30(%RBP),%XMM16	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD %XMM30,%XMM14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
VMOVAPD %XMM3,%XMM30	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVAPD %XMM4,%XMM13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
JMP 236af4 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi+0x894>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
SUB %RBX,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JMP 23652c <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi+0x2cc>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
VMOVAPD %XMM1,-0x160(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM17,-0x230(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM17,%XMM17	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVDDUP %XMM8,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVDDUP %XMM11,%XMM11	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVDDUP %XMM6,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM18,-0x220(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM19,-0x210(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM16,%XMM16	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVDDUP %XMM5,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVDQA64 %XMM23,-0x1d0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM12,-0x120(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM12,%XMM12	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM30,-0x90(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM15,-0x240(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM22,-0x1e0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM28,-0x180(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM2,-0x150(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM3,-0x140(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM0,%XMM30	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVDDUP %XMM7,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVDDUP %XMM9,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOV %R9D,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x2,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVAPD %XMM20,-0x200(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM21,-0x1f0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM24,-0x1c0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM25,-0x1b0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM26,-0x1a0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM27,-0x190(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM29,-0x170(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM31,-0x130(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM4,-0x110(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
XOR %R11D,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
VMOVAPD %XMM1,-0x380(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM2,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM17,-0xf0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM8,%XMM17	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVDDUP %XMM18,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM11,%XMM18	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVDDUP %XMM19,%XMM11	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM6,%XMM19	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVDDUP %XMM20,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPS %XMM16,-0x100(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM5,%XMM16	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVDDUP %XMM10,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVDDUP %XMM13,%XMM10	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVDDUP %XMM14,%XMM13	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVDDUP %XMM15,%XMM14	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM12,%XMM15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VBROADCASTSS -0x325dc(%RIP),%XMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (6.3%)
VMOVDDUP -0x90(%RBP),%XMM12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
VMOVAPD %XMM7,%XMM20	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVAPD %XMM1,-0x370(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM3,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM6,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM21,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VBROADCASTSS -0x3260e(%RIP),%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (6.3%)
VMOVAPD %XMM11,-0x80(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM9,%XMM21	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVAPD %XMM1,-0x360(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM31,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM6,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM22,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD -0x100(%RBP),%XMM22	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD %XMM1,-0x350(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM4,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM6,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VPBROADCASTQ %XMM23,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM5,%XMM23	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVDDUP %XMM24,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM10,%XMM24	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVAPD %XMM1,-0x340(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP -0x30(%RBP),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
VMOVAPD %XMM5,-0x3e0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM25,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVDQA %XMM6,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM13,%XMM25	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVAPD %XMM2,-0x2c0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM5,-0x3d0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM26,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM14,%XMM26	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVAPD %XMM3,-0x2d0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD %XMM5,-0x3c0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM27,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM12,%XMM27	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVAPD %XMM5,-0x3b0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM28,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD -0xf0(%RBP),%XMM28	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPS %XMM1,-0x330(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPS -0xc0(%RBP),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD %XMM5,-0x3a0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM29,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM8,%XMM29	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVAPD %XMM5,-0x390(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPS %XMM1,-0x320(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP -0xe0(%RBP),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
VMOVAPS %XMM1,-0x310(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPS -0xb0(%RBP),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVDDUP %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPS %XMM1,-0x300(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVDDUP -0xd0(%RBP),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
VMOVAPS %XMM1,-0x2f0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD -0xa0(%RBP),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVDDUP %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMOVAPD %XMM1,-0x2e0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
VMOVAPD -0x240(%RBP),%XMM15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x90(%RBP),%XMM14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x230(%RBP),%XMM17	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x220(%RBP),%XMM18	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x210(%RBP),%XMM19	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x200(%RBP),%XMM20	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x1f0(%RBP),%XMM21	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x1e0(%RBP),%XMM22	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVDQA64 -0x1d0(%RBP),%XMM23	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x1c0(%RBP),%XMM24	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x1b0(%RBP),%XMM25	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x1a0(%RBP),%XMM26	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x190(%RBP),%XMM27	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x180(%RBP),%XMM28	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x170(%RBP),%XMM29	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x160(%RBP),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x150(%RBP),%XMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x140(%RBP),%XMM30	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x130(%RBP),%XMM31	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x110(%RBP),%XMM13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x30(%RBP),%XMM16	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VMOVAPD -0x120(%RBP),%XMM12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
CMP %R9,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JE 236dc2 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi+0xb62>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
VMOVAPS -0x280(%RBP),%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VUNPCKLPD -0x260(%RBP),%XMM3,%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
VMOVAPS %XMM3,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPS -0x270(%RBP),%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VUNPCKLPD -0x250(%RBP),%XMM3,%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
VMOVAPS %XMM3,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VUNPCKLPD -0x2a0(%RBP),%XMM12,%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
VMOVAPD %XMM3,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVAPD -0x2b0(%RBP),%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
VUNPCKLPD -0x290(%RBP),%XMM3,%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
VMOVAPD %XMM3,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
ADD $0x370,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A

Name	Coverage (%)	Time (s)
▼qmcplusplus::BsplineFunctor::evaluateVGL(int, int, int, double const, double, double, double, double, int) const–	0.36	0.59
○Loop 228 - BsplineFunctor.h:291-297 - exec	0.32	0.53
○Loop 229 - BsplineFunctor.h:302-336 - exec	0.02	0.04
○Loop 230 - BsplineFunctor.h:302-336 - exec	0.00	0.01
○Loop 231 - BsplineFunctor.h:291-298 - exec	0.00	0.00

Report Configuration

Vectorization

Details

Workaround

Execution units bottlenecks

Workaround

Complex instructions

Details

Type of elements and instruction set

Matching between your function (in the source code) and the binary function

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code

Vectorization

Details

Workaround

Execution units bottlenecks

Workaround

Complex instructions

Details

Type of elements and instruction set

Matching between your function (in the source code) and the binary function

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code